Predictive Analysis of Heart Health Data

Group_16

28 Nov 2023

Table of content

  • Introduction
  • Material and Methods
  • Analysis and Discussion
  • Conclusion and Perspectives
  • References

Introduction

  • Many different types of heart diseases
  • Most common: heart coronary artery disease (CAD) -> affects the blood flow to the heart
    = Decreased blood flow -> heart attacks
  • Symptoms: Chest pain, heartburn, shortness of breath, fluttering feelings in the chest,…
  • Risk factors: High blood pressure, high blood cholesterol, and smoking

Aim

  • Uncover key patterns and risk factors associated with heart diseases
  • Identify factors highly correlated with heart disease
  • Promote early disease intervention in patients

Material and Methods

Data set Overview

  • Extracted data set providing all necessary information

  • Heart Disease data set -> UCI Machine Learning Repository

  • Snapshot of heart disease prevalence in specific individuals

  • This database has 76 attributes -> focusing on a subset of 14 attributes

Results

Data Visualization

Results

Data Visualization

Results

Principal Component Analysis

Results

Logistic Regression

Discussion

We identified several key predictors of heart disease, including the type of chest pain (cp), number of detectable vessels (thal), major vessels colored by fluoroscopy (ca), and ST depression (oldpeak).

In clinical practice, the diagnosis of heart disease often involves individual differences and a multitude of complex factors. The correlated factors can provide important reference points for clinicians in the diagnostic process, helping them to identify potential risk factors for heart disease at an earlier stage, thereby improving patients’ survival chances and overall health.

In summary, our study highlights the potential value of data analysis in enhancing the diagnosis and treatment of heart disease.

References

Janosi,Andras, Steinbrunn,William, Pfisterer,Matthias, and Detrano,Robert. (1988). Heart Disease. UCI Machine Learning Repository. https://doi.org/10.24432/C52P4X.

Detrano, Robert C. et al. “International application of a new probability algorithm for the diagnosis of coronary artery disease.” The American journal of cardiology 64 5 (1989): 304-10.

Detrano R, Salcedo EE, Hobbs RE, Yiannikas J. Cardiac cinefluoroscopy as an inexpensive aid in the diagnosis of coronary artery disease. Am J Cardiol. 1986 May 1;57(13):1041-6. doi: 10.1016/0002-9149(86)90671-5. PMID: 3706156.

Ayatollahi, Haleh et al. “Predicting coronary artery disease: a comparison between two data mining algorithms.” BMC Public Health 19 (2019): n. pag.

Longo D, Fauci A, Kasper D, Hauser S. Harrison’s principles of internal medicine. 18th ed. New York: McGraw-Hill Professionals; 2011.